plot_ly() and ggplotly() functionsplot_geo()DataTableWe will work with the COVID data presented in lecture. Recall the dataset consists of COVID-19 cases and deaths in each US state during the course of the COVID epidemic.
The objective of this lab is to identify how long after cases increased deaths increased, and after cases decreased deaths decreased, and plot data to demonstrate this
## data extracted from New York Times state-level data from NYT Github repository
# https://github.com/nytimes/covid-19-data
## state-level population information from us_census_data available on GitHub repository:
# https://github.com/COVID19Tracking/associated-data/tree/master/us_census_data
# load COVID state-level data from NYT
cv_states <- as.data.frame(data.table::fread("https://raw.githubusercontent.com/nytimes/covid-19-data/master/us-states.csv"))
# load state population data
state_pops <- as.data.frame(data.table::fread("https://raw.githubusercontent.com/COVID19Tracking/associated-data/master/us_census_data/us_census_2018_population_estimates_states.csv"))
state_pops$abb <- state_pops$state
state_pops$state <- state_pops$state_name
state_pops$state_name <- NULL
cv_states <- merge(cv_states, state_pops, by="state")
head, and tail of the datadim(cv_states)
## [1] 32562 9
head(cv_states)
## state date fips cases deaths geo_id population pop_density abb
## 1 Alabama 2021-08-29 1 691451 12222 1 4887871 96.50939 AL
## 2 Alabama 2021-07-07 1 552911 11387 1 4887871 96.50939 AL
## 3 Alabama 2020-06-21 1 30021 839 1 4887871 96.50939 AL
## 4 Alabama 2020-06-10 1 21989 744 1 4887871 96.50939 AL
## 5 Alabama 2021-07-03 1 551298 11358 1 4887871 96.50939 AL
## 6 Alabama 2021-09-29 1 794773 14200 1 4887871 96.50939 AL
tail(cv_states)
## state date fips cases deaths geo_id population pop_density abb
## 32557 Wyoming 2021-07-04 56 62445 747 56 577737 5.950611 WY
## 32558 Wyoming 2021-01-22 56 50583 571 56 577737 5.950611 WY
## 32559 Wyoming 2020-05-10 56 662 7 56 577737 5.950611 WY
## 32560 Wyoming 2020-12-25 56 42664 373 56 577737 5.950611 WY
## 32561 Wyoming 2021-07-16 56 63523 760 56 577737 5.950611 WY
## 32562 Wyoming 2020-11-30 56 33305 215 56 577737 5.950611 WY
str(cv_states)
## 'data.frame': 32562 obs. of 9 variables:
## $ state : chr "Alabama" "Alabama" "Alabama" "Alabama" ...
## $ date : IDate, format: "2021-08-29" "2021-07-07" ...
## $ fips : int 1 1 1 1 1 1 1 1 1 1 ...
## $ cases : int 691451 552911 30021 21989 551298 794773 40111 63091 148206 627905 ...
## $ deaths : int 12222 11387 839 744 11358 14200 985 1265 2506 11765 ...
## $ geo_id : int 1 1 1 1 1 1 1 1 1 1 ...
## $ population : int 4887871 4887871 4887871 4887871 4887871 4887871 4887871 4887871 4887871 4887871 ...
## $ pop_density: num 96.5 96.5 96.5 96.5 96.5 ...
## $ abb : chr "AL" "AL" "AL" "AL" ...
# format the date
cv_states$date <- as.Date(cv_states$date, format="%Y-%m-%d")
# format the state and state abbreviation (abb) variables
state_list <- unique(cv_states$state)
cv_states$state <- factor(cv_states$state, levels = state_list)
abb_list <- unique(cv_states$abb)
cv_states$abb <- factor(cv_states$abb, levels = abb_list)
# order the data first by state, second by date
cv_states = cv_states[order(cv_states$state, cv_states$date),]
# Confirm the variables are now correctly formatted
str(cv_states)
## 'data.frame': 32562 obs. of 9 variables:
## $ state : Factor w/ 52 levels "Alabama","Alaska",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ date : Date, format: "2020-03-13" "2020-03-14" ...
## $ fips : int 1 1 1 1 1 1 1 1 1 1 ...
## $ cases : int 6 12 23 29 39 51 78 106 131 157 ...
## $ deaths : int 0 0 0 0 0 0 0 0 0 0 ...
## $ geo_id : int 1 1 1 1 1 1 1 1 1 1 ...
## $ population : int 4887871 4887871 4887871 4887871 4887871 4887871 4887871 4887871 4887871 4887871 ...
## $ pop_density: num 96.5 96.5 96.5 96.5 96.5 ...
## $ abb : Factor w/ 52 levels "AL","AK","AZ",..: 1 1 1 1 1 1 1 1 1 1 ...
head(cv_states)
## state date fips cases deaths geo_id population pop_density abb
## 436 Alabama 2020-03-13 1 6 0 1 4887871 96.50939 AL
## 243 Alabama 2020-03-14 1 12 0 1 4887871 96.50939 AL
## 50 Alabama 2020-03-15 1 23 0 1 4887871 96.50939 AL
## 472 Alabama 2020-03-16 1 29 0 1 4887871 96.50939 AL
## 157 Alabama 2020-03-17 1 39 0 1 4887871 96.50939 AL
## 89 Alabama 2020-03-18 1 51 0 1 4887871 96.50939 AL
tail(cv_states)
## state date fips cases deaths geo_id population pop_density abb
## 32208 Wyoming 2021-11-12 56 107483 1298 56 577737 5.950611 WY
## 32144 Wyoming 2021-11-13 56 107483 1298 56 577737 5.950611 WY
## 32162 Wyoming 2021-11-14 56 107483 1298 56 577737 5.950611 WY
## 31982 Wyoming 2021-11-15 56 108103 1298 56 577737 5.950611 WY
## 32314 Wyoming 2021-11-16 56 108413 1347 56 577737 5.950611 WY
## 32206 Wyoming 2021-11-17 56 108658 1347 56 577737 5.950611 WY
# Inspect the range values for each variable. What is the date range? The range of cases and deaths?
head(cv_states)
## state date fips cases deaths geo_id population pop_density abb
## 436 Alabama 2020-03-13 1 6 0 1 4887871 96.50939 AL
## 243 Alabama 2020-03-14 1 12 0 1 4887871 96.50939 AL
## 50 Alabama 2020-03-15 1 23 0 1 4887871 96.50939 AL
## 472 Alabama 2020-03-16 1 29 0 1 4887871 96.50939 AL
## 157 Alabama 2020-03-17 1 39 0 1 4887871 96.50939 AL
## 89 Alabama 2020-03-18 1 51 0 1 4887871 96.50939 AL
summary(cv_states)
## state date fips cases
## Washington : 667 Min. :2020-01-21 Min. : 1.00 Min. : 1
## Illinois : 664 1st Qu.:2020-08-05 1st Qu.:16.00 1st Qu.: 32536
## California : 663 Median :2021-01-08 Median :29.00 Median : 149252
## Arizona : 662 Mean :2021-01-08 Mean :29.78 Mean : 391586
## Massachusetts: 656 3rd Qu.:2021-06-14 3rd Qu.:44.00 3rd Qu.: 489216
## Wisconsin : 652 Max. :2021-11-17 Max. :72.00 Max. :5024415
## (Other) :28598
## deaths geo_id population pop_density
## Min. : 0 Min. : 1.00 Min. : 577737 Min. : 1.292
## 1st Qu.: 632 1st Qu.:16.00 1st Qu.: 1805832 1st Qu.: 43.659
## Median : 2688 Median :29.00 Median : 4468402 Median : 107.860
## Mean : 7227 Mean :29.78 Mean : 6433123 Mean : 422.524
## 3rd Qu.: 8534 3rd Qu.:44.00 3rd Qu.: 7535591 3rd Qu.: 229.511
## Max. :73614 Max. :72.00 Max. :39557045 Max. :11490.120
## NA's :615
## abb
## WA : 667
## IL : 664
## CA : 663
## AZ : 662
## MA : 656
## WI : 652
## (Other):28598
min(cv_states$date)
## [1] "2020-01-21"
max(cv_states$date)
## [1] "2021-11-17"
new_cases and new_deaths and correct outliersAdd variables for new cases, new_cases, and new deaths, new_deaths:
new_cases is equal to the difference between cases on date i and date i-1, starting on date i=2Use plotly for EDA: See if there are outliers or values that don’t make sense for new_cases and new_deaths. Which states and which dates have strange values?
Correct outliers: Set negative values for new_cases or new_deaths to 0
Recalculate cases and deaths as cumulative sum of updates new_cases and new_deaths
# Add variables for new_cases and new_deaths:
for (i in 1:length(state_list)) {
cv_subset = subset(cv_states, state == state_list[i])
cv_subset = cv_subset[order(cv_subset$date),]
# add starting level for new cases and deaths
cv_subset$new_cases = cv_subset$cases[1]
cv_subset$new_deaths = cv_subset$deaths[1]
for (j in 2:nrow(cv_subset)) {
cv_subset$new_cases[j] = cv_subset$cases[j] - cv_subset$cases[j-1]
cv_subset$new_deaths[j] = cv_subset$deaths[j] - cv_subset$deaths[j-1]
}
# include in main dataset
cv_states$new_cases[cv_states$state==state_list[i]] = cv_subset$new_cases
cv_states$new_deaths[cv_states$state==state_list[i]] = cv_subset$new_deaths
}
# Inspect outliers using plotly
p1<-ggplot(cv_states, aes(x = date, y = new_cases, color = state)) + geom_line() + geom_point(size = .5, alpha = 0.5)
ggplotly(p1)
p1<-NULL # to clear from workspace
p2<-ggplot(cv_states, aes(x = date, y = new_deaths, color = state)) + geom_line() + geom_point(size = .5, alpha = 0.5)
ggplotly(p2)
p2<-NULL # to clear from workspace
# set negative new case or death counts to 0
cv_states$new_cases[cv_states$new_cases<0] = 0
cv_states$new_deaths[cv_states$new_deaths<0] = 0
# Recalculate `cases` and `deaths` as cumulative sum of updates `new_cases` and `new_deaths`
for (i in 1:length(state_list)) {
cv_subset = subset(cv_states, state == state_list[i])
# add starting level for new cases and deaths
cv_subset$cases = cv_subset$cases[1]
cv_subset$deaths = cv_subset$deaths[1]
for (j in 2:nrow(cv_subset)) {
cv_subset$cases[j] = cv_subset$new_cases[j] + cv_subset$cases[j-1]
cv_subset$deaths[j] = cv_subset$new_deaths[j] + cv_subset$deaths[j-1]
}
# include in main dataset
cv_states$cases[cv_states$state==state_list[i]] = cv_subset$cases
cv_states$deaths[cv_states$state==state_list[i]] = cv_subset$deaths
}
Add population-normalized (by 100,000) variables for each variable type (rounded to 1 decimal place). Make sure the variables you calculate are in the correct format (numeric). You can use the following variable names:
per100k = cases per 100,000 populationnewper100k= new cases per 100,000deathsper100k = deaths per 100,000newdeathsper100k = new deaths per 100,000Add a “naive CFR” variable representing deaths / cases on each date for each state
Create a dataframe representing values on the most recent date, cv_states_today, as done in lecture
# add population normalized (by 100,000) counts for each variable
cv_states$per100k = as.numeric(format(round(cv_states$cases/(cv_states$population/100000),1),nsmall=1))
cv_states$newper100k = as.numeric(format(round(cv_states$new_cases/(cv_states$population/100000),1),nsmall=1))
cv_states$deathsper100k = as.numeric(format(round(cv_states$deaths/(cv_states$population/100000),1),nsmall=1))
cv_states$newdeathsper100k = as.numeric(format(round(cv_states$new_deaths/(cv_states$population/100000),1),nsmall=1))
# add a naive_CFR variable = deaths / cases
cv_states = cv_states %>% mutate(naive_CFR = round((deaths*100/cases),2))
# create a `cv_states_today` variable
cv_states_today = subset(cv_states, date==max(cv_states$date))
plot_ly()plot_ly() representing pop_density vs. various variables (e.g. cases, per100k, deaths, deathsper100k) for each state on most recent date (cv_states_today)
hovermode = "compare"# pop_density vs. cases
cv_states_today %>%
plot_ly(x = ~pop_density, y = ~cases,
type = 'scatter', mode = 'markers', color = ~state,
size = ~population, sizes = c(5, 70), marker = list(sizemode='diameter', opacity=0.5))
# filter out "District of Columbia"
cv_states_today_scatter <- cv_states_today %>% filter(state!="District of Columbia")
# pop_density vs. cases after filtering
cv_states_today_scatter %>% filter(state!="District of Columbia") %>%
plot_ly(x = ~pop_density, y = ~cases,
type = 'scatter', mode = 'markers', color = ~state,
size = ~population, sizes = c(5, 70), marker = list(sizemode='diameter', opacity=0.5))
# pop_density vs. deathsper100k
cv_states_today_scatter %>% filter(state!="District of Columbia") %>%
plot_ly(x = ~pop_density, y = ~deathsper100k, z = ~population,
type = 'scatter', mode = 'markers', color = ~state,
size = ~population, sizes = c(5, 70), marker = list(sizemode='diameter', opacity=0.5))
# Adding hoverinfo
cv_states_today_scatter %>%
plot_ly(x = ~pop_density, y = ~deathsper100k,
type = 'scatter', mode = 'markers', color = ~state,
size = ~population, sizes = c(5, 70), marker = list(sizemode='diameter', opacity=0.5),
hoverinfo = 'text',
text = ~paste( paste(state, ":", sep=""), paste(" Cases per 100k: ", per100k, sep="") , paste(" Deaths per 100k: ",
deathsper100k, sep=""), sep = "<br>")) %>%
layout(title = "Population-normalized COVID-19 deaths (per 100k) vs. population density for US states",
yaxis = list(title = "Deaths per 100k"), xaxis = list(title = "Population Density"),
hovermode = "compare")
ggplotly() and geom_smooth()pop_density vs. newdeathsper100k create a chart with the same variables using gglot_ly()geom_smooth()
pop_density is a correlate of newdeathsper100k?p <- ggplot(cv_states_today_scatter, aes(x=pop_density, y=deathsper100k, size=population)) + geom_point() + geom_smooth()
ggplotly(p)
naive_CFR for all states over time using plot_ly()
naive_CFR for the states that had a “first peak” in September. How have they changed over time?new_cases and new_deaths together in one plot. Hint: use add_layer()
# Line chart for naive_CFR for all states over time using `plot_ly()`
plot_ly(cv_states, x = ~date, y = ~naive_CFR, color = ~state, type = "scatter", mode = "lines")
# Line chart for Texas showing new_cases and new_deaths together
cv_states %>% filter(state=="Texas") %>% plot_ly(x = ~date, y = ~new_cases, type = "scatter", mode = "lines") %>% add_lines(x = ~date, y = ~new_deaths, type = "scatter", mode = "lines")
Create a heatmap to visualize new_cases for each state on each date greater than April 1st, 2020 - Start by mapping selected features in the dataframe into a matrix using the tidyr package function pivot_wider(), naming the rows and columns, as done in the lecture notes - Use plot_ly() to create a heatmap out of this matrix - Create a second heatmap in which the pattern of new_cases for each state over time becomes more clear by filtering to only look at dates every two weeks
# Map state, date, and new_cases to a matrix
library(tidyr)
cv_states_mat <- cv_states %>% select(state, date, new_cases) %>% filter(date>as.Date("2020-04-01"))
cv_states_mat2 <- as.data.frame(pivot_wider(cv_states_mat, names_from = state, values_from = new_cases))
rownames(cv_states_mat2) <- cv_states_mat2$date
cv_states_mat2$date <- NULL
cv_states_mat2 <- as.matrix(cv_states_mat2)
# Create a heatmap using plot_ly()
plot_ly(x=colnames(cv_states_mat2), y=rownames(cv_states_mat2),
z=~cv_states_mat2,
type="heatmap",
showscale=T)
# Create a second heatmap after filtering to only include dates every other week
filter_dates <- seq(as.Date("2020-04-01"), as.Date("2020-10-01"), by="2 weeks")
cv_states_mat <- cv_states %>% select(state, date, new_cases) %>% filter(date %in% filter_dates)
cv_states_mat2 <- as.data.frame(pivot_wider(cv_states_mat, names_from = state, values_from = new_cases))
rownames(cv_states_mat2) <- cv_states_mat2$date
cv_states_mat2$date <- NULL
cv_states_mat2 <- as.matrix(cv_states_mat2)
# Create a heatmap using plot_ly()
plot_ly(x=colnames(cv_states_mat2), y=rownames(cv_states_mat2),
z=~cv_states_mat2,
type="heatmap",
showscale=T)
naive_CFR by state on May 1st, 2020naive_CFR by state on most recent datesubplot(). Make sure the shading is for the same range of values (google is your friend for this)### For May 1 2020
# Extract the data for each state by its abbreviation
cv_CFR <- cv_states %>% filter(date=="2020-05-01") %>% select(state, abb, naive_CFR, cases, deaths) # select data
cv_CFR$state_name <- cv_CFR$state
cv_CFR$state <- cv_CFR$abb
cv_CFR$abb <- NULL
# Create hover text
cv_CFR$hover <- with(cv_CFR, paste(state_name, '<br>', "CFR: ", naive_CFR, '<br>', "Cases: ", cases, '<br>', "Deaths: ", deaths))
# Set up mapping details
set_map_details <- list(
scope = 'usa',
projection = list(type = 'albers usa'),
showlakes = TRUE,
lakecolor = toRGB('white')
)
# Make sure both maps are on the same color scale
shadeLimit <- 9
# Create the map
fig <- plot_geo(cv_CFR, locationmode = 'USA-states') %>%
add_trace(
z = ~naive_CFR, text = ~hover, locations = ~state,
color = ~naive_CFR, colors = 'Purples'
)
fig <- fig %>% colorbar(title = "CFR May 1 2020", limits = c(0,shadeLimit))
fig <- fig %>% layout(
title = paste('CFR by State as of', Sys.Date(), '<br>(Hover for value)'),
geo = set_map_details
)
fig_May1 <- fig
#############
### For Today
# Extract the data for each state by its abbreviation
cv_CFR <- cv_states_today %>% select(state, abb, naive_CFR, cases, deaths) # select data
cv_CFR$state_name <- cv_CFR$state
cv_CFR$state <- cv_CFR$abb
cv_CFR$abb <- NULL
# Create hover text
cv_CFR$hover <- with(cv_CFR, paste(state_name, '<br>', "CFR: ", naive_CFR, '<br>', "Cases: ", cases, '<br>', "Deaths: ", deaths))
# Set up mapping details
set_map_details <- list(
scope = 'usa',
projection = list(type = 'albers usa'),
showlakes = TRUE,
lakecolor = toRGB('white')
)
# Create the map
fig <- plot_geo(cv_CFR, locationmode = 'USA-states') %>%
add_trace(
z = ~naive_CFR, text = ~hover, locations = ~state,
color = ~naive_CFR, colors = 'Purples'
)
fig <- fig %>% colorbar(title = "CFR May 1 2020", limits = c(0,shadeLimit))
fig <- fig %>% layout(
title = paste('CFR by State as of', Sys.Date(), '<br>(Hover for value)'),
geo = set_map_details
)
fig_Today <- fig
### Plot together
subplot(fig_May1, fig_Today)